{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T10:50:15Z","timestamp":1775731815738,"version":"3.50.1"},"reference-count":49,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP)","award":["2022-0-00970"],"award-info":[{"award-number":["2022-0-00970"]}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP)","award":["2020-0-01077"],"award-info":[{"award-number":["2020-0-01077"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Network pruning reduces the number of parameters and computational costs of convolutional neural networks while maintaining high performance. Although existing pruning methods have achieved excellent results, they do not consider reconstruction after pruning in order to apply the network to actual devices. This study proposes a reconstruction process for channel-based network pruning. For lossless reconstruction, we focus on three components of the network: the residual block, skip connection, and convolution layer. Union operation and index alignment are applied to the residual block and skip connection, respectively. Furthermore, we reconstruct a compressed convolution layer by considering batch normalization. We apply our method to existing channel-based pruning methods for downstream tasks such as image classification, object detection, and semantic segmentation. Experimental results show that compressing a large model has a 1.93% higher accuracy in image classification, 2.2 higher mean Intersection over Union (mIoU) in semantic segmentation, and 0.054 higher mean Average Precision (mAP) in object detection than well-designed small models. Moreover, we demonstrate that our method can reduce the actual latency by 8.15\u00d7 and 5.29\u00d7 on Raspberry Pi and Jetson Nano, respectively.<\/jats:p>","DOI":"10.3390\/s23042102","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T07:01:23Z","timestamp":1676271683000},"page":"2102","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Lossless Reconstruction of Convolutional Neural Network for Channel-Based Network Pruning"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7428-8228","authenticated-orcid":false,"given":"Donghyeon","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Control and Robot Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunho","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Control and Robot Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3400-0493","authenticated-orcid":false,"given":"Youngbae","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Control and Robot Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,13]]},"reference":[{"key":"ref_1","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_3","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Feng, S., Fan, Y., Tang, Y., Cheng, H., Zhao, C., Zhu, Y., and Cheng, C. (2022). A Change Detection Method Based on Multi-Scale Adaptive Convolution Kernel Network and Multimodal Conditional Random Field for Multi-Temporal Multispectral Images. Remote Sens., 14.","DOI":"10.3390\/rs14215368"},{"key":"ref_8","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., and Shum, H.Y. (2022). Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_11","unstructured":"Paszke, A., Chaurasia, A., Kim, S., and Culurciello, E. (2016). Enet: A deep neural network architecture for real-time semantic segmentation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Saini, V.K., Kumar, R., Mathur, A., and Saxena, A. (2020, January 7\u20138). Short term forecasting based on hourly wind speed data using deep learning algorithms. Proceedings of the 2020 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE), Jaipur, India.","DOI":"10.1109\/ICETCE48199.2020.9091757"},{"key":"ref_13","unstructured":"Han, S., Pool, J., Tran, J., and Dally, W. (2015, January 7\u201312). Learning both weights and connections for efficient neural network. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_14","unstructured":"Han, S., Mao, H., and Dally, W.J. (2015, January 7\u20139). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_15","unstructured":"Dong, X., Chen, S., and Pan, S. (2017, January 4\u20139). Learning to prune deep neural networks via layer-wise optimal brain surgeon. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_16","unstructured":"Xiao, X., Wang, Z., and Rajasekaran, S. (2019, January 8\u201314). Autoprune: Automatic network pruning by regularizing auxiliary parameters. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, CA, USA."},{"key":"ref_17","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2016). Pruning filters for efficient convnets. arXiv."},{"key":"ref_18","unstructured":"Ye, J., Lu, X., Lin, Z., and Wang, J.Z. (May, January 30). Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"He, Y., Liu, P., Wang, Z., Hu, Z., and Yang, Y. (2019, January 15\u201320). Filter pruning via geometric median for deep convolutional neural networks acceleration. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref_20","unstructured":"Liu, Z., Mu, H., Zhang, X., Guo, Z., Yang, X., Cheng, K.T., and Sun, J. (November, January 27). Metapruning: Meta learning for automatic neural network channel pruning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chin, T.W., Ding, R., Zhang, C., and Marculescu, D. (2020, January 13\u201319). Towards efficient model compression via learned global ranking. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00159"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gao, S., Huang, F., Cai, W., and Huang, H. (2021, January 19\u201325). Network pruning via performance maximization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00915"},{"key":"ref_23","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2021, January 19\u201325). Multi-Stage Progressive Image Restoration. Proceedings of the CVPR, Online.","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18\u201324). A convnet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_26","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_27","unstructured":"Zoph, B., and Le, Q.V. (2017, January 24\u201326). Neural architecture search with reinforcement learning. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_28","unstructured":"Liu, H., Simonyan, K., and Yang, Y. (2018). Darts: Differentiable architecture search. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., and Doll\u00e1r, P. (2020, January 13\u201319). Designing network design spaces. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref_30","unstructured":"LeCun, Y., Denker, J., and Solla, S. (1989, January 27\u201330). Optimal brain damage. Proceedings of the Advances in Neural Information Processing Systems, NIPS Conference, Denver, CO, USA."},{"key":"ref_31","unstructured":"Hassibi, B., and Stork, D. (December, January 30). Second order derivatives for network pruning: Optimal brain surgeon. Proceedings of the Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_32","unstructured":"Aghasi, A., Abdi, A., Nguyen, N., and Romberg, J. (2017, January 4\u20139). Net-trim: Convex pruning of deep neural networks with performance guarantee. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_33","unstructured":"Hu, H., Peng, R., Tai, Y.W., and Tang, C.K. (2016). Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv."},{"key":"ref_34","unstructured":"Molchanov, D., Ashukha, A., and Vetrov, D. (2017, January 6\u201311). Variational dropout sparsifies deep neural networks. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lee, E., and Hwang, Y. (2021). Layer-Wise Network Compression Using Gaussian Mixture Model. Electronics, 10.","DOI":"10.3390\/electronics10010072"},{"key":"ref_36","first-page":"25668","article-title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","volume":"Volume 162","author":"Chaudhuri","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wimmer, P., Mehnert, J., and Condurache, A. (2022, January 18\u201324). Interspace Pruning: Using Adaptive Filter Representations To Improve Training of Sparse CNNs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01220"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Luo, J.H., Wu, J., and Lin, W. (2017, January 22\u201329). Thinet: A filter level pruning method for deep neural network compression. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Chen, C.F., Lai, J.H., Morariu, V.I., Han, X., Gao, M., Lin, C.Y., and Davis, L.S. (2018, January 18\u201323). Nisp: Pruning networks using neuron importance score propagation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref_40","unstructured":"Li, Y., Gu, S., Zhang, K., Van Gool, L., and Timofte, R. (2020). Proceedings of the European Conference on Computer Vision, Springer."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Li, Y., Adamczewski, K., Li, W., Gu, S., Timofte, R., and Van Gool, L. (2022, January 18\u201324). Revisiting Random Channel Pruning for Neural Network Compression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Shen, M., Molchanov, P., Yin, H., and Alvarez, J.M. (2022, January 18\u201324). When to prune? a policy towards early structural pruning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01193"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Hou, Z., Qin, M., Sun, F., Ma, X., Yuan, K., Xu, Y., Chen, Y.K., Jin, R., Xie, Y., and Kung, S.Y. (2022, January 18\u201324). CHEX: CHannel EXploration for CNN Model Compression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01197"},{"key":"ref_44","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 7\u20139). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International conference on machine learning, PMLR, Lille, France."},{"key":"ref_45","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The pascal visual object classes challenge: A retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_48","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Curtin, B.H., and Matthews, S.J. (2019, January 10\u201312). Deep learning for inexpensive image classification of wildlife on the Raspberry Pi. Proceedings of the 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York, NY, USA.","DOI":"10.1109\/UEMCON47517.2019.8993061"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/2102\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:33:35Z","timestamp":1760121215000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/4\/2102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,13]]},"references-count":49,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23042102"],"URL":"https:\/\/doi.org\/10.3390\/s23042102","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,13]]}}}